Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    seat or seats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क
    1.75
    ').
    1.73
    '
    1.71
    ians
    1.66
     spie
    1.66
    ᱽ
    1.63
    は何
    1.57
    רים
    1.54
    ']].
    1.53
    ',
    1.50
    POSITIVE LOGITS
    ول
    2.73
     hidrográf
    2.22
    را
    1.98
    მწიფ
    1.90
     caída
    1.87
    ୁ
    1.85
     көзге
    1.82
    ों
    1.81
     وإن
    1.78
     स्वयं
    1.77
    Act Density 0.003%

    No Known Activations